How to Use the Elai AI Video MCP in Mastra AI

Q: Can I create an approval step for Elai AI Video workflows with Mastra AI?

Yes, Mastra's requireToolApproval is perfect for this. You can design a workflow where an agent calls createnewaivideo to make a draft, but requires human approval in a separate system before it's allowed to call triggervideorendering on the Elai AI Video MCP server.

Q: How does Mastra AI connect to the MCP server?

It's straightforward. You instantiate Mastra's MCPClient and pass it the unique Vinkius endpoint URL for your Elai MCP server subscription. Mastra handles the authentication and transport details for you.

Build resilient video automation with Elai AI Video and Mastra AI. Handle failures, retries, and notifications automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Elai AI Video MCP to Mastra AI

Create your Vinkius account to connect Elai AI Video to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Elai AI Video with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Your Entire Video Pipeline

Define a complete, hands-off video production workflow. Your Mastra agent starts by taking a script and calling `create_new_ai_video`. Mastra's engine guarantees the step runs, managing state along the way. Next, the agent calls `trigger_video_rendering`. If the Elai API is temporarily unavailable, Mastra’s built-in exponential backoff handles the retries for you. Once rendering is done, your workflow can use `get_video_details` to confirm the status and then trigger a Slack notification. Mastra's engine handles the interaction with the MCP server so you don't have to write boilerplate code.

Build Conditional Video Workflows

This is where Mastra shines. You can build real logic into your automation. For example, the first step in your agent could be to call `get_elai_account_metadata` to check your rendering credits. If the balance is below a threshold, the workflow branches to send an alert instead of creating a new video. You can also design workflows that choose an avatar from `list_available_avatars` based on the input script's topic. Mastra makes it easy to define these `if/then` steps in code, and this MCP server gives you the tools to get the data needed for those decisions.

Manage Rendering and Asset Delivery

Stop writing cron jobs to check for finished videos. Set up a Mastra agent that runs on a schedule, calls `list_successfully_rendered_videos`, and compares the results against its internal state to find new videos. For each new video, the agent can download the asset and upload it to your own S3 bucket or content delivery network. Because Mastra manages the workflow's state, you don't have to worry about processing the same video twice or losing track of a job.

Setup guide

Set up Elai AI Video MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Elai AI Video tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "elai-ai-video-mcp-client",
  servers: {
    "elai-ai-video-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Elai AI Video Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Elai AI Video tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Elai AI Video transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Elai AI Video. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Elai AI Video now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Elai AI Video MCP in Mastra AI

You don't have to do much. When your Mastra agent calls a tool like `trigger_video_rendering`, Mastra's workflow engine automatically retries the call with exponential backoff if it fails due to a network error or a temporary API issue. You can configure the retry policy.

Yes, Mastra's `requireToolApproval` is perfect for this. You can design a workflow where an agent calls `create_new_ai_video` to make a draft, but requires human approval in a separate system before it's allowed to call `trigger_video_rendering` on the Elai AI Video MCP server.

Make it the first step. Before any video creation logic, have your agent call `get_elai_account_metadata`. Then, use a conditional step to check if `credits_balance` is above a certain number. If not, the workflow can stop and send an alert.

It's straightforward. You instantiate Mastra's `MCPClient` and pass it the unique Vinkius endpoint URL for your Elai MCP server subscription. Mastra handles the authentication and transport details for you.

When a workflow runs, your Mastra agent sends video script data, template IDs, and other configuration details to the MCP server to execute tools. This data is processed inside Vinkius's isolated sandbox and is not persisted by Vinkius after the tool call is complete.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript